Viseron - Self-hosted NVR with object detection

Viseron is a self-hosted, local only NVR implemented in Python.
The goal is ease of use while also leveraging hardware acceleration for minimal system load.

Notable features

• Records videos on detected objects

• Supports multiple different object detectors:

  • YOLOv3/4 Darknet using OpenCV
  • Tensorflow via Google Coral EdgeTPU
  • DeepStack

• Motion detection

• Face recognition via:

  • dlib
  • DeepStack

• Lookback, buffers frames to record before the event actually happened

• Multiarch Docker containers for ease of use.

• Supports hardware acceleration on different platforms

  • CUDA for systems with a supported GPU
  • OpenCL
  • OpenMax and MMAL on the RaspberryPi 3B+
  • video4linux on the RaspberryPi 4
  • Intel QuickSync with VA-API
  • NVIDIA video4linux2 on Jetson Nano

• Multiplatform, should support any amd64, aarch64 or armhf machine running Linux.
  Specific images are built to support:

  • RaspberryPi 3B+
  • RaspberryPi 4
  • NVIDIA Jetson Nano

  Builds are tested and verified on the following platforms:

  • Ubuntu 18.04 with NVIDIA GPU
  • Ubuntu 18.04 running on an Intel NUC
  • RaspberryPi 3B+

• Native support for RTSP and MJPEG

• Zones to limit detection to a particular area to reduce false positives

• Masks to limit where motion detection occurs

• Stop/start cameras on-demand over MQTT

• Home Assistant integration via MQTT

• unRAID Community Application

Table of Contents

• Supported architectures
• Getting started
• Contributing
• Configuration Options
  • Cameras
    • Substream
    • Camera motion detection
    • Camera object detection
    • Mask
    • Zones
    • Points
    • Static MJPEG streams
  • Object detection
    • Darknet
    • EdgeTPU
    • DeepStack
    • Labels
  • Motion detection
    • Background subtractor
    • Background subtractor MOG2
  • Recorder
  • User Interface
    • Dynamic MJPEG streams
  • Post Processors
    • Face Recognition
      • dlib
      • DeepStack
  • MQTT
    • Topics for each camera
    • Topics for each Viseron instance
    • Home Assistant MQTT Discovery
  • Logging
  • Secrets
• Benchmarks
• User and Group Identifiers

Supported architectures

Viserons images support multiple architectures such as amd64, aarch64 and armhf.
Pulling roflcoopter/viseron:latest should automatically pull the correct image for you. An exception to this is if you have the need for a specific container, eg the CUDA version.
Then you will need to specify your desired image.

The images available are:

Getting started

Choose the appropriate docker container for your machine. Builds are published to Docker Hub

docker run --rm \
--privileged \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
-v /opt/vc/lib:/opt/vc/lib \
--name viseron \
--device /dev/vchiq:/dev/vchiq \
--device /dev/vcsm:/dev/vcsm \
--device /dev/bus/usb:/dev/bus/usb \
roflcoopter/viseron:latest

version: "2.4"
services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
      - /opt/vc/lib:/opt/vc/lib
    devices:
      - /dev/vchiq:/dev/vchiq
      - /dev/vcsm:/dev/vcsm
      - /dev/bus/usb:/dev/bus/usb
    privileged: true

docker run --rm \
--privileged \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
-v /dev/bus/usb:/dev/bus/usb \
-v /opt/vc/lib:/opt/vc/lib \
--name viseron \
--device=/dev/video10:/dev/video10 \
--device=/dev/video11:/dev/video11 \
--device=/dev/video12:/dev/video12 \
--device /dev/bus/usb:/dev/bus/usb \
roflcoopter/viseron:latest

version: "2.4"
services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    devices:
      - /dev/video10:/dev/video10
      - /dev/video11:/dev/video11
      - /dev/video12:/dev/video12
      - /dev/bus/usb:/dev/bus/usb
    privileged: true

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
roflcoopter/viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
--device /dev/dri \
roflcoopter/viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    devices:
      - /dev/dri

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
--runtime=nvidia \
roflcoopter/amd64-cuda-viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/amd64-cuda-viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    runtime: nvidia

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
--runtime=nvidia \
--privileged \
roflcoopter/jetson-nano-viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/jetson-nano-viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    runtime: nvidia
    privileged: true

VAAPI support is built into every amd64 container. To utilize it you need to add --device /dev/dri to your docker command.
EdgeTPU support is also included in all containers. To use it, add -v /dev/bus/usb:/dev/bus/usb --privileged to your docker command.

The config.yaml has to be mounted to the folder /config.
If no config is present, a default minimal one will be created.
Here you need to fill in at least your cameras and you should be good to go.

Contributing

Contributors to the project are very much appreciated. See the contribution guidelines on how to get started.

Some things you can help with:

• Implement an open feature request or issue from the issue tracker
• Improve the documentation
• Answer questions in issues or discussions

You can also use the links below to sponsor Viseron or make a one time donation.

Configuration Options

Cameras

cameras:
  - name: Front door
    mqtt_name: viseron_front_door
    host: 192.168.30.2
    port: 554
    username: user
    password: pass
    path: /Streaming/Channels/101/
    width: 1920
    height: 1080
    fps: 6 
    motion_detection:
      interval: 1
      trigger_detector: false
    object_detection:
      interval: 1
      labels:
        - label: person
          confidence: 0.9
        - label: pottedplant
          confidence: 0.9

Used to build the FFmpeg command to decode camera stream.
The command is built like this:
"ffmpeg" + global_args + input_args + hwaccel_args + codec + "-rtsp_transport tcp -i " + (stream url) + filter_args + output_args

Default FFmpeg decoder command

A default FFmpeg decoder command is generated, which varies a bit depending on the Docker container you use,

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -c:v h264_cuvid -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -hwaccel vaapi -vaapi_device /dev/dri/renderD128 -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

ffmpeg -hide_banner -loglevel panic -avoid_negative_ts make_zero -fflags nobuffer -flags low_delay -strict experimental -fflags +genpts -stimeout 5000000 -use_wallclock_as_timestamps 1 -vsync 0 -c:v h264_mmal -rtsp_transport tcp -i rtsp://<username>:<password>@<host>:<port><path> -f rawvideo -pix_fmt nv12 pipe:1

This means that you do not have to set hwaccel_args unless you have a specific need to change the default command (say you need to change h264_cuvid to hevc_cuvid)

FFmpeg recoverable errors

Sometimes FFmpeg prints errors which are not fatal, such as [h264 @ 0x55b1e115d400] error while decoding MB 0 12, bytestream 114567.
Viseron always performs a sanity check on the FFmpeg decoder command with -loglevel fatal.
If Viseron gets stuck on an error that you believe is not fatal, you can add a subset of that error to ffmpeg_recoverable_errors.
So to ignore the error above you would add this to your configuration:

ffmpeg_recoverable_errors:
  - error while decoding MB

FFprobe stream information

Viseron needs to know the width, height, FPS and audio/video codecs of your stream.
FFprobe is used on initialization to figure all this information out.

Some cameras dont play nice with this and fail to report some information.
To circumvent this you can manually specify all these options.

If you specify all of width, height, fps, codec and audio_codec, Viseron will not need to call FFprobe and startup will be significantly faster.

Substream

Using the substream is a great way to reduce the system load from FFmpeg.
When configured, two FFmpeg processes will spawn:
- One that reads the main stream and creates segments for recordings. Codec -c:v copy is used so practically no resources are used.
- One that reads the substream and pipes frames to Viseron for motion/object detection.

To really benefit from this you should reduce the framerate of the substream to match the lowest interval set for either motion or object detection.
As an example:

motion_detection:
  interval: 0.5
object_detection:
  interval: 1

The optimal FPS for this config would be 2, since it would output a frame every 0.5 seconds for the motion detector to consume.

You should also change the resolution to something lower than the main stream to benefit from this.

Camera motion detection

Refer to the global motion detection config.
Note that you must use the same type for each camera.
Each setting set here overrides the global motion detection config.

Camera object detection

Mask

cameras:
  - name: name
    host: ip
    port: port
    path: /Streaming/Channels/101/
    motion_detection:
      area: 0.07
      mask:
        - points:
            - x: 0
              y: 0
            - x: 250
              y: 0
            - x: 250
              y: 250
            - x: 0
              y: 250
        - points:
            - x: 500
              y: 500
            - x: 1000
              y: 500
            - x: 1000
              y: 750
            - x: 300
              y: 750
    object_detection:
      area: 0.07
      mask:
        - points:
            - x: 0
              y: 0
            - x: 250
              y: 0
            - x: 250
              y: 250
            - x: 0
              y: 250
        - points:
            - x: 400
              y: 200
            - x: 1000
              y: 200
            - x: 1000
              y: 750
            - x: 400
              y: 750

Masks are used to exclude certain areas in the image from motion or object detection depending on the configuration.
Say you have a camera which is filming some trees. When the wind is blowing, motion will probably be detected.
Add a mask under the cameras motion_detection block that cover these trees and they will no longer trigger said motion.

To ignore all objects in a certain area, add a mask under the cameras object_detection block that covers the area.

Zones

cameras:
  - name: name
    host: ip
    port: port
    path: /Streaming/Channels/101/
    zones:
      - name: zone1
        points:
          - x: 0
            y: 500
          - x: 1920
            y: 500
          - x: 1920
            y: 1080
          - x: 0
            y: 1080
        labels:
          - label: person
            confidence: 0.9
      - name: zone2
        points:
          - x: 0
            y: 0
          - x: 500
            y: 0
          - x: 500
            y: 500
          - x: 0
            y: 500
        labels:
          - label: cat
            confidence: 0.5

Zones are used to define areas in the cameras field of view where you want to look for certain objects(labels).

Say you have a camera facing the sidewalk and have labels setup to look for and record a person.
This would cause Viseron to start recording people who are walking past the camera on the sidewalk. Not ideal.
To remedy this you define a zone which covers only the area that you are actually interested in, excluding the sidewalk.

Points

Points are used to form a polygon for a zone or a object/motion detection mask.

To easily generate points you can use a tool like image-map.net.
Just upload an image from your camera and start drawing your zone.
Then click Show me the code! and adapt it to the config format.
Coordinates coords="522,11,729,275,333,603,171,97" should be turned into this:

points:
  - x: 522
    y: 11
  - x: 729
    y: 275
  - x: 333
    y: 603
  - x: 171
    y: 97

Static MJPEG Streams

cameras:
  - name: Front door
    host: 192.168.30.2
    port: 554
    username: user
    password: pass
    path: /Streaming/Channels/101/
    static_mjpeg_streams:
      my-big-front-door-stream:
        width: 1920
        height: 1080
        draw_objects: True
      my-small-front-door-stream:
        width: 100
        height: 100
        draw_objects: True

Viseron can serve predefined MJPEG streams.
This is useful for debugging, but also if you want to view your camera on a Chromecast for instance.

The MJPEG streams work exactly as the dynamic streams which uses query parameters.
The benefit of using these predefined streams instead is that frame processing happens only once.
This means that you can theoretically have as many streams open as you want without increased load on your machine.

The config example above would give you two streams, available at these endpoints:
http://localhost:8888/front_door/static-mjpeg-streams/my-big-front-door-stream
http://localhost:8888/front_door/static-mjpeg-streams/my-small-front-door-stream

Object detection

object_detection:
  type: darknet
  interval: 6
  labels:
    - label: person
      confidence: 0.9
      height_min: 0.1481
      height_max: 0.7
      width_min: 0.0598
      width_max: 0.36
    - label: truck
      confidence: 0.8

The above options are global for all types of detectors.
If loglevel is set to DEBUG, all detected objects will be printed in a statement like this:

[2020-09-29 07:57:23] [viseron.nvr.<camera name>.object ] [DEBUG   ] - Objects: [{'label': 'chair', 'confidence': 0.618, 'rel_width': 0.121, 'rel_height': 0.426, 'rel_x1': 0.615, 'rel_y1': 0.423, 'rel_x2': 0.736, 'rel_y2': 0.849}, {'label': 'pottedplant', 'confidence': 0.911, 'rel_width': 0.193, 'rel_height': 0.339, 'rel_x1': 0.805, 'rel_y1': 0.466, 'rel_x2': 0.998, 'rel_y2': 0.805}, {'label': 'pottedplant', 'confidence': 0.786, 'rel_width': 0.065, 'rel_height': 0.168, 'rel_x1': 0.522, 'rel_y1': 0.094, 'rel_x2': 0.587, 'rel_y2': 0.262}, {'label': 'pottedplant', 'confidence': 0.532, 'rel_width': 0.156, 'rel_height': 0.159, 'rel_x1': 0.644, 'rel_y1': 0.317, 'rel_x2': 0.8, 'rel_y2': 0.476}]

Darknet

The above options are specific to the type: darknet detector. The included models are placed inside /detectors/models/darknet folder.
The default model differs a bit per container:

• roflcoopter/viseron: This one uses YOLOv3 by default.
• roflcoopter/amd64-viseron: This one uses YOLOv3 by default.
• roflcoopter/amd64-cuda-viseron: This one uses YOLOv4 by default.

The reason why not all containers are using YOLOv4 is that there are currently some issues with OpenCVs implementation of it.
As soon as this is fixed for the versions of OpenCV that Viseron is using, YOLOv4 will be the standard for all.

The containers using YOLOv3 also has YOLOv3-tiny included in the image.
YOLOv3-tiny can be used to reduce CPU usage, but will have significantly worse accuracy. If you want to swap to YOLOv3-tiny you can change these configuration options:

object_detection:
  model_path: /detectors/models/darknet/yolov3-tiny.weights
  model_config: /detectors/models/darknet/yolov3-tiny.cfg

EdgeTPU

The above options are specific to the type: edgetpu detector.
The included models are placed inside /detectors/models/edgetpu folder.
There are two models available, one that runs on the EdgeTPU and one the runs on the CPU.

DeepStack Objects

The above options are specific to the type: deepstack detector.

DeepStack is a self-hosted, free and open source AI server that provides, among other functions, object detection.
It is highly optimized and runs on a pleathora of devices and platforms.
Below is quoted from DeepStacks documentation:

DeepStack is an AI server that empowers every developer in the world to easily build state-of-the-art AI systems both on premise and in the cloud. The promises of Artificial Intelligence are huge but becoming a machine learning engineer is hard. DeepStack is device and language agnostic. You can run it on Windows, Mac OS, Linux, Raspberry PI and use it with any programming language.
DeepStack’s source code is available on GitHub via https://github.com/johnolafenwa/DeepStack
DeepStack is developed and maintained by DeepQuest AI

Labels

Labels are used to tell Viseron what objects to look for and keep recordings of.
The available labels depends on what detection model you are using.
For the built in models you can check the label_path file to see which labels that are available, see commands below.

The max/min width/height is used to filter out any unreasonably large/small objects to reduce false positives.
Objects can also be filtered out with the use of an optional mask.

Important: Viseron defaults to track label: person. This means that if you want not track any label at all you have to explicitly do so like this:

object_detection:
  labels: []

Motion detection

motion_detection:
  interval: 1
  trigger_detector: true
  timeout: true
  max_timeout: 30
  width: 300
  height: 300
  area: 0.1
  frames: 3

The above options are global for all types of motion detectors detectors.

Background subtractor

The above options are specific to the type: background_subtractor detector.\

Motion detection works by creating a running average of frames, and then comparing the current frame to this average.
If enough changes have occurred, motion will be detected.
By using a running average, the "background" image will adjust to daylight, stationary objects etc.
This blogpost from PyImageSearch explains this procedure quite well.

Background subtractor MOG2

The above options are specific to the type: mog2 detector.

Performs motion detection using the Background subtraction MOG2 algorithm.

Recorder

recorder:
  lookback: 10
  timeout: 10
  retain: 7
  folder: /recordings

Viseron uses FFmpeg segments to handle recordings.
This means Viseron will write small 5 second segments of the stream to disk, and in case of any recording starting, Viseron will find the appropriate segments and concatenate them together.
The reason for using segments instead of just starting the recorder on an event, is to support to the lookback feature which makes it possible to record before an event actually happened.

ffmpeg -hide_banner -loglevel error -y -protocol_whitelist file,pipe -f concat -safe 0 -i - -c:v copy <outfile.mp4>

If you want to re-encode the video you can choose codec, filter_args and optionally hwaccel_args.
To place the segments in memory instead of writing to disk, you can mount a tmpfs disk in the container.

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--tmpfs /tmp \
--name viseron \
roflcoopter/viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    tmpfs:
      - /tmp

recorder:
  segments_folder: /tmp

Thumbnail

The default location for the thumbnail if save_to_disk: true is /recordings/{camera_name}/latest_thumbnail.jpg

User Interface

The user interface can be reached by default on port 8888 inside the container.

Dynamic MJPEG Streams

Viseron will serve MJPEG streams of all cameras.
The stream can be reached on a slugified version of the configured camera name with _ as separator.
If you are unsure on your camera name in this format you can run this snippet:
docker exec -it viseron python3 -c "from viseron.config import CONFIG; from viseron.helpers import print_slugs; print_slugs(CONFIG);"

Example URL: http://localhost:8888/<camera name slug>/mjpeg-stream

To increase performance it is recommended to use static streams instead.

Query parameters

A number of query parameters are available to instruct Viseron to resize the stream or draw different things in the image.
To utilize a parameter you append it to the URL after a ?. To add multiple parameters you separate them with & like this:
http://localhost:8888/<camera name slug>/mjpeg-stream?<parameter1>=<value>&<parameter2>=<value>

Post Processors

post_processors:
  face_recognition:
    type: dlib
    expire_after: 10
  logging:
    level: info

Post processors are used when you want to perform some kind of action when a specific object is detected.
Right now the only implemented post processor is face recognition. In the future more of these post processors will be added (ALPR) along with the ability to create your own custom post processors.

Face Recognition

On startup images are read from face_recognition_path and a model is trained to recognize these faces.
The folder structure of the faces folder is very strict. Here is an example of the default one:

/config
|-- face_recognition
|   `-- faces
|       |-- person1
|       |   |-- image_of_person1_1.jpg
|       |   |-- image_of_person1_2.png
|       |   `-- image_of_person1_3.jpg
|       `-- person2
|       |   |-- image_of_person2_1.jpeg
|       |   `-- image_of_person2_2.jpg

The above options are global for all types of face recognition.

dlib

The above options are specific to type: dlib face recognition.

DeepStack Faces

The above options are specific to type: deepstack face recognition.

DeepStack is a self-hosted, free and open source AI server that provides, among other functions, face recognition.
It is highly optimized and runs on a pleathora of devices and platforms.
Below is quoted from DeepStacks documentation:

DeepStack is an AI server that empowers every developer in the world to easily build state-of-the-art AI systems both on premise and in the cloud. The promises of Artificial Intelligence are huge but becoming a machine learning engineer is hard. DeepStack is device and language agnostic. You can run it on Windows, Mac OS, Linux, Raspberry PI and use it with any programming language.
DeepStack’s source code is available on GitHub via https://github.com/johnolafenwa/DeepStack
DeepStack is developed and maintained by DeepQuest AI

MQTT

mqtt:
  broker: mqtt_broker.lan
  port: 1883
  username: user
  password: pass

Topics for each camera

{"state": "scanning_for_objects", "attributes": {"last_recording_start": <timestamp>, "last_recording_end": <timestamp>}}

{"state": "on", "attributes": {}}

{"state": "on", "attributes": {"objects": [{"label": "person", "confidence": 0.961, "rel_width": 0.196, "rel_height": 0.359, "rel_x1": 0.804, "rel_y1": 0.47, "rel_x2": 1.0, "rel_y2": 0.829}]}}

{"state": "on", "attributes": {"count": 2}}

{"state": "on", "attributes": {}}

{"state": "on", "attributes": {"objects": [{"label": "person", "confidence": 0.961, "rel_width": 0.196, "rel_height": 0.359, "rel_x1": 0.804, "rel_y1": 0.47, "rel_x2": 1.0, "rel_y2": 0.829}]}}

{"state": "on", "attributes": {"count": 2}}

Topics for each Viseron instance

{"state": "on", "attributes": {}}

All MQTT topics are largely inspired by Home Assistants way of organizing entities.

Home Assistant MQTT Discovery

Viseron integrates into Home Assistant using MQTT discovery and is enabled by default if you configure MQTT.
Viseron will create a number of entities depending on your configuration.

Cameras
A variable amount of cameras will be created based on your configuration.

1. A camera entity to debug zones, masks, objects and motion.
   Images are only sent to this topic if publish_image: true
2. If send_to_mqtt under recorder is set to true , a camera entity named camera.{client_id from mqtt config}_{mqtt_name from camera config}_latest_thumbnail is created

Sensor
A sensor entity is created for each camera which indicates the status of Viseron. The state is set to recording, scanning_for_motion or scanning_for_objects depending on the situation.

Binary Sensors
A variable amount of binary sensors will be created based on your configuration.

1. A binary sensor showing if any tracked object is in view.
2. A binary sensor for each tracked object showing if the label is in view.
3. A binary sensor for each zone showing if any tracked object is in the zone.
4. A binary sensor for each tracked object in a zone showing if the label is in the zone.
5. A binary sensor showing if motion is detected.
6. A binary sensor showing if a face is detected.

Switch
A switch entity will be created for each camera.
The switch is used to arm/disarm a camera. When disarmed, no system resources are used for the camera.

Logging

logging:
  level: debug

Secrets

Any value in config.yaml can be substituted with secrets stored in secrets.yaml.
This can be used to remove any private information from your config.yaml to make it easier to share your config.yaml with others.

The secrets.yaml is expected to be in the same folder as config.yaml.
The full path needs to be /config/secrets.yaml.

Here is a simple usage example.
Contents of /config/secrets.yaml:

camera_ip: 192.168.1.2
username: coolusername
password: supersecretpassword

Contents of /config/config.yaml:

cameras:
  - name: Front Door
    host: !secret camera_ip
    username: !secret username
    password: !secret password

User and Group Identifiers

When using volumes (-v flags) permissions issues can happen between the host and the container. To solve this, you can specify the user PUID and group PGID as environment variables to the container.

docker run --rm \
-v <recordings path>:/recordings \
-v <config path>:/config \
-v /etc/localtime:/etc/localtime:ro \
--name viseron \
-e PUID=1000 \
-e PGID=1000 \
roflcoopter/viseron:latest

version: "2.4"

services:
  viseron:
    image: roflcoopter/viseron:latest
    container_name: viseron
    volumes:
      - <recordings path>:/recordings
      - <config path>:/config
      - /etc/localtime:/etc/localtime:ro
    environment:
      - PUID=1000
      - PGID=1000

Ensure the volumes are owned on the host by the user you specify. In this example PUID=1000 and PGID=1000.

To find the UID and GID of your current user you can run this command on the host:

  $ id your_username_here

Viseron runs as root (PUID=0 and PGID=0) by default.
This is because it can be problematic to get hardware acceleration and/or EdgeTPUs to work properly for everyone.
The s6-overlay init scripts do a good job at fixing permissions for other users, but you may still face some issues if you choose to not run as root.
If you do have issues, please open an issue and i will do my best to fix them.

Benchmarks

Here I will show you the system load on a few different machines/configs.
All examples are with one camera running 1920x1080 at 6 FPS.
Motion and object detection running at a 1 second interval.

Intel i3-9350K CPU @ 4.00GHz 4 cores with NVIDIA GTX1660 Ti

Intel NUC NUC7i5BNH (Intel i5-7260U CPU @ 2.20GHz 2 cores) using VAAPI and OpenCL

Intel NUC NUC7i5BNH (Intel i5-7260U CPU @ 2.20GHz 2 cores) without VAAPI or OpenCL

Tips

• If you are experiencing issues with a camera, I suggest you add debug logging to it and examine the logs

Ideas and upcoming features

• UI

  • Create a UI for configuration and viewing of recordings

• Detectors

  • Pause detection via MQTT
  • Allow specified confidence to override height/width thresholds
  • Dynamic detection interval, speed up interval when detection happens for all types of detectors
  • Implement an object tracker for detected objects
  • Make it easier to implement custom detectors

• Recorder

  • Weaving, If detection is triggered close to previous detection, send silent alarm and "weave" the videos together.
  • Dynamic lookback based on motion

https://devblogs.nvidia.com/object-detection-pipeline-gpus/

Donations are very appreciated and will go directly into more hardware for Viseron to support.